Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17277
    Prev
    Next
    INDEX
    Explanations

    the numerical value "tens" used to describe large quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of people or things, particularly in tens of thousands or millions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     techno
    -0.65
     Sachs
    -0.61
     Mate
    -0.59
     Samoa
    -0.58
     sucker
    -0.58
     planner
    -0.57
     Proposition
    -0.57
     captivity
    -0.57
     Orbital
    -0.57
     Hust
    -0.55
    POSITIVE LOGITS
    atile
    1.09
    earchers
    1.06
    omet
    1.03
    atility
    0.99
    elfth
    0.96
    entimes
    0.93
    arios
    0.92
    ourcing
    0.91
    eteen
    0.90
    kies
    0.88
    Activations Density 0.028%

    No Known Activations